© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6348
    Prev
    Next
    INDEX
    Explanations

    locations in Germany

    oai_token-act-pair · gemini-2.0-flash

    technical or formal terms

    np_token-act-pair-logits · gpt-4o-mini

    German locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dar
    -0.41
     vz
    -0.40
     sos
    -0.40
    स्प
    -0.39
    vello
    -0.39
     momentum
    -0.38
    weber
    -0.38
     singoli
    -0.38
     Caught
    -0.38
    !*\
    -0.37
    POSITIVE LOGITS
    WireFormatLite
    0.81
    thâu
    0.72
     resourceCulture
    0.68
    </tfoot>
    0.68
     Monfieur
    0.67
    المناصب
    0.67
     OnEnable
    0.65
    ScopeManager
    0.64
     EconPapers
    0.63
     itſelf
    0.63
    Activations Density 0.317%

    No Known Activations